Microsoft on its Blog, a couple of days ago, announced to launch a cloud service that uses Artificial Intelligence to track down bugs in software. The company will soon start offering a preview version of the tool for Linux users as well.
Microsoft Security Risk Detection, previously known as Project Springfield, is a cloud-based tool that developers can use to look for bugs and other security vulnerabilities in the software. The tool is designed to identify the vulnerabilities before the software into production. This, the company claims, will save users from the heartache of having to patch a bug, deal with crashes or respond to an attack after it has been released.
David Molnar, the Microsoft researcher who leads the group delivering the risk detection tool, said companies have traditionally hired security experts to do this kind of work, which is called fuzz testing if they did it at all.
This service from Microsoft is unique because it uses artificial intelligence to as a series of “what if” questions to try to root out what might trigger a crash and signal a security concern.
It is interesting to notice the growing influence of AI in the cyber security arena. Somewhere during last year, a host of security vendors and testers started talking about AI and machine learning as the Holy Grail for improving the capabilities of detecting and responding to security breaches. There is little doubt that the algorithms used in AI can help a great deal in uncovering the threats. AI is capable of assisting in a few specific areas such as identification of threats, risk assessment, and orchestration of remediation.
IBM also launched its Cognitive SOC – a platform that embeds Watson for Cyber Security’s, which gives the ability to understand, reason and learn about security topics and threats. By tapping into and making sense of structured and unstructured security knowledge, it augments a security analyst’s ability to fill gaps in intelligence, speed, and accuracy.
Yakir Golan, Co-founder & CEO at myDRO in his blog published last year in Venture Beat wrote that lightweight AI-based prediction models, which can reside and operate autonomously even on low computing power devices, can enable detection and blocking of suspicious activity in real time on the device or at the network level.
A lot of start-ups in the cyber security space are also working on promising technologies.
Two years ago even Check Point Software acquired an Israel-based company Lacoon Mobile Security, which uses AI in a big way. Lacoon not only provides the most comprehensive solution for iOS and Android but also delivers real-time mobile security and intelligence to an organization’s existing security and mobility infrastructures. Its patented technology detects device, application and in-network threats that others may have missed and quantified the risks and vulnerabilities that BYOD exposes to the enterprise.
US-based start up Jask helps users monitor networks end-to-end, using advanced AI to surface and triage the most relevant attacks while providing a clear picture of the attack surface. With instantaneous, deep knowledge about attacks, analysts can make decisions with more confidence and speed.
Yet another UK-based start-up Status Today has developed technology, which, by using Machine Learning techniques and Organizational Human Behavior, detects possible malicious behavior, no matter how big or small it is. The system doesn’t intercept data or intrude in the network, which might decrease the performance, but instead, uses a passive monitoring approach that sits behind the scene.
A Germany-based start up Neokami is leveraging breakthroughs in Artificial Intelligence. Neokami’s CyberVault enables companies to discover, secure and govern sensitive data in the cloud, on premise, or across their physical assets.
Yet another emerging cyber security player Dark Trace uses AI to spot and prevent cyber crime before they actually take place. Darktrace’s Enterprise Immune System uses AI algorithms that mimic the human immune system to defend enterprise networks of all types and sizes. Its self-learning approach is the first non-consumer application of machine learning to work at scale, across all network types, from physical, virtualized, and cloud, through to IoT and industrial control systems.
The above listed AI-based security technologies, which emerged only in the recent years show a promising future wherein the integration of AI into the security systems can be of great benefit.
The developments taking place in the AI space can surely provide new tools for the threat hunters. It surely holds a promise for helping organizations protect both devices and networks even before a human being can detect or classify them.
(Image Courtesy: Pixabay.com)